Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys
This study examines the performance of three machine learning models—namely, Artificial Neural Network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN)—for spatial downscaling of seasonal forecasts of daily minimum temperature from 12 km to 250 m horizontal resolution. Downscaling i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/38 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589132960890880 |
|---|---|
| author | Sudheer Bhakare Michael Matiu Alice Crespi Dino Zardi |
| author_facet | Sudheer Bhakare Michael Matiu Alice Crespi Dino Zardi |
| author_sort | Sudheer Bhakare |
| collection | DOAJ |
| description | This study examines the performance of three machine learning models—namely, Artificial Neural Network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN)—for spatial downscaling of seasonal forecasts of daily minimum temperature from 12 km to 250 m horizontal resolution. Downscaling is carried out with a one-month lead time, with analysis split into short-term (1 to 8 days) and extended (9 to 28 days) forecast periods, allowing a detailed assessment of the performance of models over time. Results suggest that CNN outperforms ANN and RF, achieving lower Root Mean Square Error (ranging from 2.04 °C to 2.66 °C) and Mean Absolute Error (1.59 °C to 2.03 °C) along with higher correlation (0.75 to 0.88) and reduced bias (−0.38 °C to −0.68) across all seasons, for the short term. The CNN model also exhibits superior performance in frost prediction, with the highest F1 score (0.78) and lowest False Discovery Rate (0.30) in predicting frost events, particularly in early spring for the short-term forecast period over 2010–2018. However, errors increase in transitional months, like April, and in the extended forecast period, confirming the intrinsic challenges inherent to predicting frost events in these months. Despite the decreased skills for extended forecast periods, results suggest that the CNN model’s effectiveness for spatial downscaling of minimum temperature and frost forecasting over complex terrain provides a valuable tool for frost risk management. |
| format | Article |
| id | doaj-art-9970e860aee74aeb81866df45ced3ec6 |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-9970e860aee74aeb81866df45ced3ec62025-01-24T13:21:47ZengMDPI AGAtmosphere2073-44332025-01-011613810.3390/atmos16010038Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine ValleysSudheer Bhakare0Michael Matiu1Alice Crespi2Dino Zardi3Center Agriculture Food Environment (C3A), University of Trento, Via Edmund Mach, 1, 38098 San Michele all’Adige, ItalyDepartment of Civil, Environmental and Mechanical Engineering (DICAM), University of Trento, Via Mesiano, 77, 38123 Trento, ItalyInstitute for Earth Observation, Eurac Research, 39100 Bolzano, ItalyCenter Agriculture Food Environment (C3A), University of Trento, Via Edmund Mach, 1, 38098 San Michele all’Adige, ItalyThis study examines the performance of three machine learning models—namely, Artificial Neural Network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN)—for spatial downscaling of seasonal forecasts of daily minimum temperature from 12 km to 250 m horizontal resolution. Downscaling is carried out with a one-month lead time, with analysis split into short-term (1 to 8 days) and extended (9 to 28 days) forecast periods, allowing a detailed assessment of the performance of models over time. Results suggest that CNN outperforms ANN and RF, achieving lower Root Mean Square Error (ranging from 2.04 °C to 2.66 °C) and Mean Absolute Error (1.59 °C to 2.03 °C) along with higher correlation (0.75 to 0.88) and reduced bias (−0.38 °C to −0.68) across all seasons, for the short term. The CNN model also exhibits superior performance in frost prediction, with the highest F1 score (0.78) and lowest False Discovery Rate (0.30) in predicting frost events, particularly in early spring for the short-term forecast period over 2010–2018. However, errors increase in transitional months, like April, and in the extended forecast period, confirming the intrinsic challenges inherent to predicting frost events in these months. Despite the decreased skills for extended forecast periods, results suggest that the CNN model’s effectiveness for spatial downscaling of minimum temperature and frost forecasting over complex terrain provides a valuable tool for frost risk management.https://www.mdpi.com/2073-4433/16/1/38minimum temperaturedownscalingneural networkrandom forestfrostAlps |
| spellingShingle | Sudheer Bhakare Michael Matiu Alice Crespi Dino Zardi Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys Atmosphere minimum temperature downscaling neural network random forest frost Alps |
| title | Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys |
| title_full | Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys |
| title_fullStr | Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys |
| title_full_unstemmed | Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys |
| title_short | Spatial Downscaling of Daily Temperature Minima Using Machine Learning Methods and Application to Frost Forecasting in Two Alpine Valleys |
| title_sort | spatial downscaling of daily temperature minima using machine learning methods and application to frost forecasting in two alpine valleys |
| topic | minimum temperature downscaling neural network random forest frost Alps |
| url | https://www.mdpi.com/2073-4433/16/1/38 |
| work_keys_str_mv | AT sudheerbhakare spatialdownscalingofdailytemperatureminimausingmachinelearningmethodsandapplicationtofrostforecastingintwoalpinevalleys AT michaelmatiu spatialdownscalingofdailytemperatureminimausingmachinelearningmethodsandapplicationtofrostforecastingintwoalpinevalleys AT alicecrespi spatialdownscalingofdailytemperatureminimausingmachinelearningmethodsandapplicationtofrostforecastingintwoalpinevalleys AT dinozardi spatialdownscalingofdailytemperatureminimausingmachinelearningmethodsandapplicationtofrostforecastingintwoalpinevalleys |